Pattern Recognition, International Conference on
Download PDF

Abstract

Some intensity independent color models are studied experimentally in the scope of visual tracking to introduce robustness to illumination changes. In addition, a plain color background model to allow modest camera motion is presented. The background is represented as a Gaussian mixture in color space. The EM algorithm is applied to find the decomposition and the Minimum Description Length principle is proposed to determine the number of mixture components. A simple tracking algorithm is outlined and the achieved results are introduced.
Like what you’re reading?
Already a member?
Get this article FREE with a new membership!